Realtime Person Identification via Gait Analysis

TL;DR

This paper introduces a compact, efficient CNN model for real-time gait-based person identification on edge devices, achieving high accuracy with minimal resource consumption, suitable for deployment on microcontrollers like Arduino.

Contribution

The paper presents a small 4-layer CNN model optimized for edge AI, capable of real-time gait recognition with high accuracy and low power usage, demonstrated on a microcontroller.

Findings

Achieved 96.7% accuracy on a 24-class gait dataset.

Model consumes only 5KB RAM and 125mW power.

Successfully demonstrated real-time identification on Arduino Nano 33 BLE Sense.

Abstract

Each person has a unique gait, i.e., walking style, that can be used as a biometric for personal identification. Recent works have demonstrated effective gait recognition using deep neural networks, however most of these works predominantly focus on classification accuracy rather than model efficiency. In order to perform gait recognition using wearable devices on the edge, it is imperative to develop highly efficient low-power models that can be deployed on to small form-factor devices such as microcontrollers. In this paper, we propose a small CNN model with 4 layers that is very amenable for edge AI deployment and realtime gait recognition. This model was trained on a public gait dataset with 20 classes augmented with data collected by the authors, aggregating to 24 classes in total. Our model achieves 96.7% accuracy and consumes only 5KB RAM with an inferencing time of 70 ms and 125mW power, while running continuous inference on Arduino Nano 33 BLE Sense. We successfully demonstrated realtime identification of the authors with the model running on Arduino, thus underscoring the efficacy and providing a proof of feasiblity for deployment in practical systems in near future.